{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:WCN6BAFCNM3SUK6MY7CYE3FM2I","short_pith_number":"pith:WCN6BAFC","schema_version":"1.0","canonical_sha256":"b09be080a26b372a2bccc7c5826cacd22adbcf4b568fb05bd13536cd5a94fd89","source":{"kind":"arxiv","id":"1407.3414","version":2},"attestation_state":"computed","paper":{"title":"Interactive Q-learning for Probabilities and Quantiles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Eric B. Laber, Kristin A. Linn, Leonard A. Stefanski","submitted_at":"2014-07-12T19:09:43Z","abstract_excerpt":"A dynamic treatment regime is a sequence of decision rules in which each decision rule recommends treatment based on features of patient medical history such as past treatments and outcomes. Existing methods for estimating optimal dynamic treatment regimes from data optimize the mean of a response variable. However, the mean may not always be the most appropriate summary of performance. We derive estimators of decision rules for optimizing probabilities and quantiles computed with respect to the response distribution for two-stage, binary treatment settings. This enables estimation of dynamic "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1407.3414","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2014-07-12T19:09:43Z","cross_cats_sorted":[],"title_canon_sha256":"082494f884232ba2f38004c608afb9e30db74b9a1d6e364e5252ed306ed8e7b2","abstract_canon_sha256":"9395ba6e097c888e851dce2ada2147f7d6c269db9be8d71a549472d932021a57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:03:55.502624Z","signature_b64":"QeJC17LqY4NGCUp4Idm4r1Gm/Lm5LHPzDsrfsrJdg2VEhRi1PvqvinsjmiE7d7ydarod1ogw2JUS55/BYME1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b09be080a26b372a2bccc7c5826cacd22adbcf4b568fb05bd13536cd5a94fd89","last_reissued_at":"2026-05-18T02:03:55.501839Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:03:55.501839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interactive Q-learning for Probabilities and Quantiles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Eric B. Laber, Kristin A. Linn, Leonard A. Stefanski","submitted_at":"2014-07-12T19:09:43Z","abstract_excerpt":"A dynamic treatment regime is a sequence of decision rules in which each decision rule recommends treatment based on features of patient medical history such as past treatments and outcomes. Existing methods for estimating optimal dynamic treatment regimes from data optimize the mean of a response variable. However, the mean may not always be the most appropriate summary of performance. We derive estimators of decision rules for optimizing probabilities and quantiles computed with respect to the response distribution for two-stage, binary treatment settings. This enables estimation of dynamic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.3414","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1407.3414","created_at":"2026-05-18T02:03:55.501957+00:00"},{"alias_kind":"arxiv_version","alias_value":"1407.3414v2","created_at":"2026-05-18T02:03:55.501957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.3414","created_at":"2026-05-18T02:03:55.501957+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCN6BAFCNM3S","created_at":"2026-05-18T12:28:54.890064+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCN6BAFCNM3SUK6M","created_at":"2026-05-18T12:28:54.890064+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCN6BAFC","created_at":"2026-05-18T12:28:54.890064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WCN6BAFCNM3SUK6MY7CYE3FM2I","json":"https://pith.science/pith/WCN6BAFCNM3SUK6MY7CYE3FM2I.json","graph_json":"https://pith.science/api/pith-number/WCN6BAFCNM3SUK6MY7CYE3FM2I/graph.json","events_json":"https://pith.science/api/pith-number/WCN6BAFCNM3SUK6MY7CYE3FM2I/events.json","paper":"https://pith.science/paper/WCN6BAFC"},"agent_actions":{"view_html":"https://pith.science/pith/WCN6BAFCNM3SUK6MY7CYE3FM2I","download_json":"https://pith.science/pith/WCN6BAFCNM3SUK6MY7CYE3FM2I.json","view_paper":"https://pith.science/paper/WCN6BAFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1407.3414&json=true","fetch_graph":"https://pith.science/api/pith-number/WCN6BAFCNM3SUK6MY7CYE3FM2I/graph.json","fetch_events":"https://pith.science/api/pith-number/WCN6BAFCNM3SUK6MY7CYE3FM2I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCN6BAFCNM3SUK6MY7CYE3FM2I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCN6BAFCNM3SUK6MY7CYE3FM2I/action/storage_attestation","attest_author":"https://pith.science/pith/WCN6BAFCNM3SUK6MY7CYE3FM2I/action/author_attestation","sign_citation":"https://pith.science/pith/WCN6BAFCNM3SUK6MY7CYE3FM2I/action/citation_signature","submit_replication":"https://pith.science/pith/WCN6BAFCNM3SUK6MY7CYE3FM2I/action/replication_record"}},"created_at":"2026-05-18T02:03:55.501957+00:00","updated_at":"2026-05-18T02:03:55.501957+00:00"}